Nonparametric panel stationarity testing with an application to crude oil production
- 12 March 2022
- journal article
- research article
- Published by Taylor & Francis in Journal of Applied Statistics
- Vol. 49 (4) , 1033-1048
Abstract
A nonparametric panel stationarity test is proposed which offers the advantage of not requiring prior specification of the trend function for each of the series in the panel. A bootstrap implementation of the test is outlined and its finite sample performance is analyzed via Monte Carlo simulations. An application is also included where the proposed test is used to analyze the stochastic properties of monthly crude oil production for a panel of 20 -both OPEC and non-OPEC- countries from 1973 to 2015. Our analysis detects strong evidence of non-stationarity, both globally and group-wise. Results have implications for the effectiveness of government intervention and stabilization policies.Keywords
Funding Information
- Ministerio de Economía e Industria (MINECO-18-ECO2017-86402-C2-1-R)
This publication has 30 references indexed in Scilit:
- Nonstationary-volatility robust panel unit root tests and the great moderationAStA Advances in Statistical Analysis, 2014
- An Intersection Test for Panel Unit RootsEconometric Reviews, 2012
- An analysis of oil production by OPEC countries: Persistence, breaks, and outliersEnergy Policy, 2011
- Global and hemispheric temperatures revisitedClimatic Change, 2008
- Panel Stationarity Test with Structural Breaks*Oxford Bulletin of Economics and Statistics, 2008
- A Stationarity Test in the Presence of an Unknown Number of Smooth BreaksJournal of Time Series Analysis, 2006
- Breaking the panels: An application to the GDP per capitaThe Econometrics Journal, 2005
- Testing for the Presence of a Random Walk in Series with Structural BreaksJournal of Time Series Analysis, 2001
- The carbon cycle and the value of forests as a carbon sink: a boreal case study2000
- Testing for stationarity in heterogeneous panel dataThe Econometrics Journal, 2000